| { | |
| "best_metric": 0.4731850028038025, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1813236627379873, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003626473254759746, | |
| "grad_norm": 0.2896139323711395, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5753, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003626473254759746, | |
| "eval_loss": 0.6112894415855408, | |
| "eval_runtime": 2.6363, | |
| "eval_samples_per_second": 18.966, | |
| "eval_steps_per_second": 4.931, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007252946509519492, | |
| "grad_norm": 0.31351906061172485, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5986, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010879419764279238, | |
| "grad_norm": 0.21199020743370056, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.5979, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014505893019038985, | |
| "grad_norm": 0.45380309224128723, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.6193, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01813236627379873, | |
| "grad_norm": 0.2842571437358856, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.6155, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.021758839528558477, | |
| "grad_norm": 0.21065452694892883, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.5999, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025385312783318223, | |
| "grad_norm": 0.19808341562747955, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.5668, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02901178603807797, | |
| "grad_norm": 0.17439045011997223, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.5716, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.032638259292837715, | |
| "grad_norm": 0.15666157007217407, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.5531, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03626473254759746, | |
| "grad_norm": 0.16270697116851807, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.5528, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03989120580235721, | |
| "grad_norm": 0.16018244624137878, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.5243, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.043517679057116954, | |
| "grad_norm": 0.1584496945142746, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.5323, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0471441523118767, | |
| "grad_norm": 0.1197987049818039, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.5528, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.050770625566636446, | |
| "grad_norm": 0.10884349048137665, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.5078, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05439709882139619, | |
| "grad_norm": 0.1160396933555603, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.529, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05802357207615594, | |
| "grad_norm": 0.12833020091056824, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.5426, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.061650045330915684, | |
| "grad_norm": 0.12921151518821716, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.5148, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06527651858567543, | |
| "grad_norm": 0.13123565912246704, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.5207, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06890299184043518, | |
| "grad_norm": 0.12849967181682587, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.5413, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07252946509519492, | |
| "grad_norm": 0.12699094414710999, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.5007, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07615593834995467, | |
| "grad_norm": 0.1284758299589157, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.52, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07978241160471441, | |
| "grad_norm": 0.13641078770160675, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.5452, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08340888485947416, | |
| "grad_norm": 0.1368888020515442, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.5092, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08703535811423391, | |
| "grad_norm": 0.16932345926761627, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.5132, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09066183136899365, | |
| "grad_norm": 0.15658120810985565, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.4985, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09066183136899365, | |
| "eval_loss": 0.4834555685520172, | |
| "eval_runtime": 2.0256, | |
| "eval_samples_per_second": 24.684, | |
| "eval_steps_per_second": 6.418, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0942883046237534, | |
| "grad_norm": 0.10247881710529327, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.5168, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09791477787851315, | |
| "grad_norm": 0.11820855736732483, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.551, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10154125113327289, | |
| "grad_norm": 0.11400573700666428, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.5089, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10516772438803264, | |
| "grad_norm": 0.1190500557422638, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.5123, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10879419764279238, | |
| "grad_norm": 0.12067992240190506, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.5113, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11242067089755213, | |
| "grad_norm": 0.12420016527175903, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.5039, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.11604714415231188, | |
| "grad_norm": 0.12639960646629333, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.4742, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.11967361740707162, | |
| "grad_norm": 0.12689970433712006, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.4927, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.12330009066183137, | |
| "grad_norm": 0.1331597864627838, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.5117, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.12692656391659113, | |
| "grad_norm": 0.13654395937919617, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.5115, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13055303717135086, | |
| "grad_norm": 0.14279140532016754, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.5082, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.13417951042611062, | |
| "grad_norm": 0.16443079710006714, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.492, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.13780598368087035, | |
| "grad_norm": 0.11059442907571793, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.5043, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1414324569356301, | |
| "grad_norm": 0.10864920914173126, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.5052, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.14505893019038985, | |
| "grad_norm": 0.10561143606901169, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.5122, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1486854034451496, | |
| "grad_norm": 0.11367624253034592, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.4875, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.15231187669990934, | |
| "grad_norm": 0.11491914838552475, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.5187, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1559383499546691, | |
| "grad_norm": 0.11767067015171051, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.5232, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.15956482320942883, | |
| "grad_norm": 0.12322618812322617, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.5039, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1631912964641886, | |
| "grad_norm": 0.13600581884384155, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.5255, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.16681776971894832, | |
| "grad_norm": 0.12546585500240326, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.505, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.17044424297370808, | |
| "grad_norm": 0.15670840442180634, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.5126, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.17407071622846781, | |
| "grad_norm": 0.13949869573116302, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.5064, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.17769718948322757, | |
| "grad_norm": 0.13772359490394592, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.4811, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1813236627379873, | |
| "grad_norm": 0.1660703420639038, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5298, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1813236627379873, | |
| "eval_loss": 0.4731850028038025, | |
| "eval_runtime": 2.0393, | |
| "eval_samples_per_second": 24.518, | |
| "eval_steps_per_second": 6.375, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.981138793183314e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |